TY - JOUR
T1 - Measuring What Explanations Actually Achieve—An Umbrella Review of Fidelity, Stability, Comprehensibility, Decision Usefulness, Human Trust, and Reliance
AU - Sarah Bennett
AU - Kwame Asante
AU - Elena Rossi
JF - Journal of Trustworthy and Explainable Intelligent Systems
JO - J Trustworthy Explain Intell Syst
Y1 - 2026
VL - 5
IS - 1
SP - 81
N2 - Explainable artificial intelligence has generated extensive technical and human-centered evaluation research, yet substantial uncertainty remains about what explanation evaluations actually demonstrate. This umbrella review synthesizes review-level evidence concerning the evaluation of fidelity, faithfulness, stability, robustness, comprehensibility, cognitive accessibility, decision usefulness, human trust, trust calibration, and reliance. Rather than reviewing explanation algorithms as methods, the article examines the constructs, metrics, study designs, and validity assumptions through which explanation quality has been assessed. The synthesis distinguishes technical correspondence with model behavior from human judgments of plausibility, understanding, usefulness, and satisfaction. It further separates human trust from system trustworthiness and behavioral reliance from beneficial decision support. Review-level evidence indicates that technical metrics are heterogeneous, terminology is inconsistently operationalized, and stable or plausible explanations are not necessarily faithful. Human-centered evaluations frequently rely on self-reported understanding, satisfaction, or trust, while objective comprehension, cognitive load, decision quality, appropriate reliance, overreliance, and underreliance receive less consistent assessment. Evidence linking technical explanation properties to downstream human and institutional outcomes remains limited, particularly across stakeholder groups, realistic decision contexts, repeated use, and changing system conditions. The umbrella synthesis therefore rejects single-metric interpretations of explanation quality and organizes evaluation as a multidimensional evidence problem involving technical validity, cognitive accessibility, decision consequences, calibrated trust, reliance behavior, accountability, and contestability. Its principal contribution is a consolidated evaluation agenda that clarifies what existing measures may support, what they do not establish, and which methodological connections require stronger user-centered, task-specific, longitudinal, and socio-technical validation.
UR - https://tipublications.com/a586440683
ER -